{"id":"https://openalex.org/W2152671254","doi":"https://doi.org/10.1109/dsn.2009.5270289","title":"System log pre-processing to improve failure prediction","display_name":"System log pre-processing to improve failure prediction","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2152671254","doi":"https://doi.org/10.1109/dsn.2009.5270289","mag":"2152671254"},"language":"en","primary_location":{"id":"doi:10.1109/dsn.2009.5270289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2009.5270289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/IFIP International Conference on Dependable Systems & Networks","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101747534","display_name":"Ziming Zheng","orcid":"https://orcid.org/0000-0002-2969-4582"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ziming Zheng","raw_affiliation_strings":["Illinois Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060400468","display_name":"Zhiling Lan","orcid":"https://orcid.org/0000-0002-1047-8724"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiling Lan","raw_affiliation_strings":["Illinois Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051307917","display_name":"Byung H. Park","orcid":"https://orcid.org/0000-0002-2387-0880"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byung H. Park","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113990568","display_name":"Al Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Al Geist","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101747534"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":10.14,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.9840361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"572","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7420409321784973},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7138507962226868},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6383649110794067},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5434035062789917},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5381774306297302},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5061659216880798},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.45046466588974},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.414157509803772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3629099130630493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7420409321784973},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7138507962226868},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6383649110794067},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5434035062789917},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5381774306297302},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5061659216880798},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.45046466588974},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.414157509803772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3629099130630493},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dsn.2009.5270289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2009.5270289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/IFIP International Conference on Dependable Systems & Networks","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.568.4455","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.568.4455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.iit.edu/~zlan/publications/dsn09_pds.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320316545","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W119004536","https://openalex.org/W208057840","https://openalex.org/W1558516248","https://openalex.org/W1984578990","https://openalex.org/W2053691501","https://openalex.org/W2061388644","https://openalex.org/W2107263349","https://openalex.org/W2140715562","https://openalex.org/W2143220335","https://openalex.org/W2150632478","https://openalex.org/W2155118768","https://openalex.org/W2155713541","https://openalex.org/W2166559705","https://openalex.org/W2171300258","https://openalex.org/W6604746331","https://openalex.org/W6608443543","https://openalex.org/W6633553838","https://openalex.org/W6646175012","https://openalex.org/W6680699518","https://openalex.org/W6680785567","https://openalex.org/W6682562027"],"related_works":["https://openalex.org/W2351192921","https://openalex.org/W2347219288","https://openalex.org/W2351383156","https://openalex.org/W143192764","https://openalex.org/W2552130520","https://openalex.org/W2950384838","https://openalex.org/W23689825","https://openalex.org/W2113904186","https://openalex.org/W4318604512","https://openalex.org/W2049287808"],"abstract_inverted_index":{"Log":[0],"preprocessing,":[1],"a":[2,11,54],"process":[3],"applied":[4],"on":[5],"the":[6,47,111,124,130],"raw":[7],"log":[8,55],"before":[9],"applying":[10],"predictive":[12],"method,":[13],"is":[14],"of":[15,60,113],"paramount":[16],"importance":[17],"to":[18,34,67,79,98,155],"failure":[19,37,43,90,93,120,144,147,151],"prediction":[20,152],"and":[21,72,82,129],"diagnosis.":[22],"While":[23],"existing":[24],"filtering":[25,78,97,103],"methods":[26],"have":[27],"demonstrated":[28],"good":[29],"compression":[30],"rate,":[31],"they":[32],"fail":[33],"preserve":[35,142],"important":[36],"patterns":[38,91,145],"that":[39,138],"are":[40],"crucial":[41],"for":[42,92,102,146],"analysis.":[44],"To":[45],"address":[46],"problem,":[48],"in":[49],"this":[50],"paper":[51],"we":[52],"present":[53],"preprocessing":[56,115],"method.":[57],"It":[58],"consists":[59],"three":[61],"integrated":[62],"steps:":[63],"(1)":[64],"event":[65,77],"categorization":[66],"uniformly":[68],"classify":[69],"system":[70,133],"events":[71,101],"identify":[73],"fatal":[74],"events;":[75],"(2)":[76],"remove":[80],"temporal":[81],"spatial":[83],"redundant":[84],"records,":[85],"while":[86],"also":[87],"preserving":[88],"necessary":[89],"analysis;":[94],"(3)":[95],"causality-related":[96],"combine":[99],"correlated":[100],"through":[104],"apriori":[105],"association":[106],"rule":[107],"mining.":[108],"We":[109],"demonstrate":[110],"effectiveness":[112],"our":[114,139],"method":[116,140],"by":[117,153],"using":[118],"real":[119],"logs":[121],"collected":[122],"from":[123],"Cray":[125],"XT4":[126],"at":[127,134],"ORNL":[128],"Blue":[131],"Gene/L":[132],"SDSC.":[135],"Experiments":[136],"show":[137],"can":[141],"more":[143],"analysis,":[148],"thereby":[149],"improving":[150],"up":[154],"174%.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}